gup.c 31 KB
Newer Older
1 2 3 4 5 6 7 8 9 10 11
#include <linux/kernel.h>
#include <linux/errno.h>
#include <linux/err.h>
#include <linux/spinlock.h>

#include <linux/mm.h>
#include <linux/pagemap.h>
#include <linux/rmap.h>
#include <linux/swap.h>
#include <linux/swapops.h>

12 13
#include <linux/sched.h>
#include <linux/rwsem.h>
14
#include <linux/hugetlb.h>
15 16
#include <asm/pgtable.h>

17 18
#include "internal.h"

19 20
static struct page *no_page_table(struct vm_area_struct *vma,
		unsigned int flags)
21
{
22 23 24 25 26 27 28 29 30 31 32 33
	/*
	 * When core dumping an enormous anonymous area that nobody
	 * has touched so far, we don't want to allocate unnecessary pages or
	 * page tables.  Return error instead of NULL to skip handle_mm_fault,
	 * then get_dump_page() will return NULL to leave a hole in the dump.
	 * But we can only make this optimization where a hole would surely
	 * be zero-filled if handle_mm_fault() actually did handle it.
	 */
	if ((flags & FOLL_DUMP) && (!vma->vm_ops || !vma->vm_ops->fault))
		return ERR_PTR(-EFAULT);
	return NULL;
}
34

35 36 37 38 39 40 41
static struct page *follow_page_pte(struct vm_area_struct *vma,
		unsigned long address, pmd_t *pmd, unsigned int flags)
{
	struct mm_struct *mm = vma->vm_mm;
	struct page *page;
	spinlock_t *ptl;
	pte_t *ptep, pte;
42

43
retry:
44
	if (unlikely(pmd_bad(*pmd)))
45
		return no_page_table(vma, flags);
46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64

	ptep = pte_offset_map_lock(mm, pmd, address, &ptl);
	pte = *ptep;
	if (!pte_present(pte)) {
		swp_entry_t entry;
		/*
		 * KSM's break_ksm() relies upon recognizing a ksm page
		 * even while it is being migrated, so for that case we
		 * need migration_entry_wait().
		 */
		if (likely(!(flags & FOLL_MIGRATION)))
			goto no_page;
		if (pte_none(pte) || pte_file(pte))
			goto no_page;
		entry = pte_to_swp_entry(pte);
		if (!is_migration_entry(entry))
			goto no_page;
		pte_unmap_unlock(ptep, ptl);
		migration_entry_wait(mm, pmd, address);
65
		goto retry;
66 67 68
	}
	if ((flags & FOLL_NUMA) && pte_numa(pte))
		goto no_page;
69 70 71 72
	if ((flags & FOLL_WRITE) && !pte_write(pte)) {
		pte_unmap_unlock(ptep, ptl);
		return NULL;
	}
73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125

	page = vm_normal_page(vma, address, pte);
	if (unlikely(!page)) {
		if ((flags & FOLL_DUMP) ||
		    !is_zero_pfn(pte_pfn(pte)))
			goto bad_page;
		page = pte_page(pte);
	}

	if (flags & FOLL_GET)
		get_page_foll(page);
	if (flags & FOLL_TOUCH) {
		if ((flags & FOLL_WRITE) &&
		    !pte_dirty(pte) && !PageDirty(page))
			set_page_dirty(page);
		/*
		 * pte_mkyoung() would be more correct here, but atomic care
		 * is needed to avoid losing the dirty bit: it is easier to use
		 * mark_page_accessed().
		 */
		mark_page_accessed(page);
	}
	if ((flags & FOLL_MLOCK) && (vma->vm_flags & VM_LOCKED)) {
		/*
		 * The preliminary mapping check is mainly to avoid the
		 * pointless overhead of lock_page on the ZERO_PAGE
		 * which might bounce very badly if there is contention.
		 *
		 * If the page is already locked, we don't need to
		 * handle it now - vmscan will handle it later if and
		 * when it attempts to reclaim the page.
		 */
		if (page->mapping && trylock_page(page)) {
			lru_add_drain();  /* push cached pages to LRU */
			/*
			 * Because we lock page here, and migration is
			 * blocked by the pte's page reference, and we
			 * know the page is still mapped, we don't even
			 * need to check for file-cache page truncation.
			 */
			mlock_vma_page(page);
			unlock_page(page);
		}
	}
	pte_unmap_unlock(ptep, ptl);
	return page;
bad_page:
	pte_unmap_unlock(ptep, ptl);
	return ERR_PTR(-EFAULT);

no_page:
	pte_unmap_unlock(ptep, ptl);
	if (!pte_none(pte))
126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158
		return NULL;
	return no_page_table(vma, flags);
}

/**
 * follow_page_mask - look up a page descriptor from a user-virtual address
 * @vma: vm_area_struct mapping @address
 * @address: virtual address to look up
 * @flags: flags modifying lookup behaviour
 * @page_mask: on output, *page_mask is set according to the size of the page
 *
 * @flags can have FOLL_ flags set, defined in <linux/mm.h>
 *
 * Returns the mapped (struct page *), %NULL if no mapping exists, or
 * an error pointer if there is a mapping to something not represented
 * by a page descriptor (see also vm_normal_page()).
 */
struct page *follow_page_mask(struct vm_area_struct *vma,
			      unsigned long address, unsigned int flags,
			      unsigned int *page_mask)
{
	pgd_t *pgd;
	pud_t *pud;
	pmd_t *pmd;
	spinlock_t *ptl;
	struct page *page;
	struct mm_struct *mm = vma->vm_mm;

	*page_mask = 0;

	page = follow_huge_addr(mm, address, flags & FOLL_WRITE);
	if (!IS_ERR(page)) {
		BUG_ON(flags & FOLL_GET);
159
		return page;
160
	}
161

162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218
	pgd = pgd_offset(mm, address);
	if (pgd_none(*pgd) || unlikely(pgd_bad(*pgd)))
		return no_page_table(vma, flags);

	pud = pud_offset(pgd, address);
	if (pud_none(*pud))
		return no_page_table(vma, flags);
	if (pud_huge(*pud) && vma->vm_flags & VM_HUGETLB) {
		if (flags & FOLL_GET)
			return NULL;
		page = follow_huge_pud(mm, address, pud, flags & FOLL_WRITE);
		return page;
	}
	if (unlikely(pud_bad(*pud)))
		return no_page_table(vma, flags);

	pmd = pmd_offset(pud, address);
	if (pmd_none(*pmd))
		return no_page_table(vma, flags);
	if (pmd_huge(*pmd) && vma->vm_flags & VM_HUGETLB) {
		page = follow_huge_pmd(mm, address, pmd, flags & FOLL_WRITE);
		if (flags & FOLL_GET) {
			/*
			 * Refcount on tail pages are not well-defined and
			 * shouldn't be taken. The caller should handle a NULL
			 * return when trying to follow tail pages.
			 */
			if (PageHead(page))
				get_page(page);
			else
				page = NULL;
		}
		return page;
	}
	if ((flags & FOLL_NUMA) && pmd_numa(*pmd))
		return no_page_table(vma, flags);
	if (pmd_trans_huge(*pmd)) {
		if (flags & FOLL_SPLIT) {
			split_huge_page_pmd(vma, address, pmd);
			return follow_page_pte(vma, address, pmd, flags);
		}
		ptl = pmd_lock(mm, pmd);
		if (likely(pmd_trans_huge(*pmd))) {
			if (unlikely(pmd_trans_splitting(*pmd))) {
				spin_unlock(ptl);
				wait_split_huge_page(vma->anon_vma, pmd);
			} else {
				page = follow_trans_huge_pmd(vma, address,
							     pmd, flags);
				spin_unlock(ptl);
				*page_mask = HPAGE_PMD_NR - 1;
				return page;
			}
		} else
			spin_unlock(ptl);
	}
	return follow_page_pte(vma, address, pmd, flags);
219 220
}

221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264
static int get_gate_page(struct mm_struct *mm, unsigned long address,
		unsigned int gup_flags, struct vm_area_struct **vma,
		struct page **page)
{
	pgd_t *pgd;
	pud_t *pud;
	pmd_t *pmd;
	pte_t *pte;
	int ret = -EFAULT;

	/* user gate pages are read-only */
	if (gup_flags & FOLL_WRITE)
		return -EFAULT;
	if (address > TASK_SIZE)
		pgd = pgd_offset_k(address);
	else
		pgd = pgd_offset_gate(mm, address);
	BUG_ON(pgd_none(*pgd));
	pud = pud_offset(pgd, address);
	BUG_ON(pud_none(*pud));
	pmd = pmd_offset(pud, address);
	if (pmd_none(*pmd))
		return -EFAULT;
	VM_BUG_ON(pmd_trans_huge(*pmd));
	pte = pte_offset_map(pmd, address);
	if (pte_none(*pte))
		goto unmap;
	*vma = get_gate_vma(mm);
	if (!page)
		goto out;
	*page = vm_normal_page(*vma, address, *pte);
	if (!*page) {
		if ((gup_flags & FOLL_DUMP) || !is_zero_pfn(pte_pfn(*pte)))
			goto unmap;
		*page = pte_page(*pte);
	}
	get_page(*page);
out:
	ret = 0;
unmap:
	pte_unmap(pte);
	return ret;
}

265 266 267 268 269
/*
 * mmap_sem must be held on entry.  If @nonblocking != NULL and
 * *@flags does not include FOLL_NOWAIT, the mmap_sem may be released.
 * If it is, *@nonblocking will be set to 0 and -EBUSY returned.
 */
270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287
static int faultin_page(struct task_struct *tsk, struct vm_area_struct *vma,
		unsigned long address, unsigned int *flags, int *nonblocking)
{
	struct mm_struct *mm = vma->vm_mm;
	unsigned int fault_flags = 0;
	int ret;

	/* For mlock, just skip the stack guard page. */
	if ((*flags & FOLL_MLOCK) &&
			(stack_guard_page_start(vma, address) ||
			 stack_guard_page_end(vma, address + PAGE_SIZE)))
		return -ENOENT;
	if (*flags & FOLL_WRITE)
		fault_flags |= FAULT_FLAG_WRITE;
	if (nonblocking)
		fault_flags |= FAULT_FLAG_ALLOW_RETRY;
	if (*flags & FOLL_NOWAIT)
		fault_flags |= FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_RETRY_NOWAIT;
288 289 290 291
	if (*flags & FOLL_TRIED) {
		VM_WARN_ON_ONCE(fault_flags & FAULT_FLAG_ALLOW_RETRY);
		fault_flags |= FAULT_FLAG_TRIED;
	}
292 293 294 295 296 297 298

	ret = handle_mm_fault(mm, vma, address, fault_flags);
	if (ret & VM_FAULT_ERROR) {
		if (ret & VM_FAULT_OOM)
			return -ENOMEM;
		if (ret & (VM_FAULT_HWPOISON | VM_FAULT_HWPOISON_LARGE))
			return *flags & FOLL_HWPOISON ? -EHWPOISON : -EFAULT;
299
		if (ret & (VM_FAULT_SIGBUS | VM_FAULT_SIGSEGV))
300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330
			return -EFAULT;
		BUG();
	}

	if (tsk) {
		if (ret & VM_FAULT_MAJOR)
			tsk->maj_flt++;
		else
			tsk->min_flt++;
	}

	if (ret & VM_FAULT_RETRY) {
		if (nonblocking)
			*nonblocking = 0;
		return -EBUSY;
	}

	/*
	 * The VM_FAULT_WRITE bit tells us that do_wp_page has broken COW when
	 * necessary, even if maybe_mkwrite decided not to set pte_write. We
	 * can thus safely do subsequent page lookups as if they were reads.
	 * But only do so when looping for pte_write is futile: in some cases
	 * userspace may also be wanting to write to the gotten user page,
	 * which a read fault here might prevent (a readonly page might get
	 * reCOWed by userspace write).
	 */
	if ((ret & VM_FAULT_WRITE) && !(vma->vm_flags & VM_WRITE))
		*flags &= ~FOLL_WRITE;
	return 0;
}

331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368
static int check_vma_flags(struct vm_area_struct *vma, unsigned long gup_flags)
{
	vm_flags_t vm_flags = vma->vm_flags;

	if (vm_flags & (VM_IO | VM_PFNMAP))
		return -EFAULT;

	if (gup_flags & FOLL_WRITE) {
		if (!(vm_flags & VM_WRITE)) {
			if (!(gup_flags & FOLL_FORCE))
				return -EFAULT;
			/*
			 * We used to let the write,force case do COW in a
			 * VM_MAYWRITE VM_SHARED !VM_WRITE vma, so ptrace could
			 * set a breakpoint in a read-only mapping of an
			 * executable, without corrupting the file (yet only
			 * when that file had been opened for writing!).
			 * Anon pages in shared mappings are surprising: now
			 * just reject it.
			 */
			if (!is_cow_mapping(vm_flags)) {
				WARN_ON_ONCE(vm_flags & VM_MAYWRITE);
				return -EFAULT;
			}
		}
	} else if (!(vm_flags & VM_READ)) {
		if (!(gup_flags & FOLL_FORCE))
			return -EFAULT;
		/*
		 * Is there actually any vma we can reach here which does not
		 * have VM_MAYREAD set?
		 */
		if (!(vm_flags & VM_MAYREAD))
			return -EFAULT;
	}
	return 0;
}

369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388
/**
 * __get_user_pages() - pin user pages in memory
 * @tsk:	task_struct of target task
 * @mm:		mm_struct of target mm
 * @start:	starting user address
 * @nr_pages:	number of pages from start to pin
 * @gup_flags:	flags modifying pin behaviour
 * @pages:	array that receives pointers to the pages pinned.
 *		Should be at least nr_pages long. Or NULL, if caller
 *		only intends to ensure the pages are faulted in.
 * @vmas:	array of pointers to vmas corresponding to each page.
 *		Or NULL if the caller does not require them.
 * @nonblocking: whether waiting for disk IO or mmap_sem contention
 *
 * Returns number of pages pinned. This may be fewer than the number
 * requested. If nr_pages is 0 or negative, returns 0. If no pages
 * were pinned, returns -errno. Each page returned must be released
 * with a put_page() call when it is finished with. vmas will only
 * remain valid while mmap_sem is held.
 *
389
 * Must be called with mmap_sem held.  It may be released.  See below.
390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411
 *
 * __get_user_pages walks a process's page tables and takes a reference to
 * each struct page that each user address corresponds to at a given
 * instant. That is, it takes the page that would be accessed if a user
 * thread accesses the given user virtual address at that instant.
 *
 * This does not guarantee that the page exists in the user mappings when
 * __get_user_pages returns, and there may even be a completely different
 * page there in some cases (eg. if mmapped pagecache has been invalidated
 * and subsequently re faulted). However it does guarantee that the page
 * won't be freed completely. And mostly callers simply care that the page
 * contains data that was valid *at some point in time*. Typically, an IO
 * or similar operation cannot guarantee anything stronger anyway because
 * locks can't be held over the syscall boundary.
 *
 * If @gup_flags & FOLL_WRITE == 0, the page must not be written to. If
 * the page is written to, set_page_dirty (or set_page_dirty_lock, as
 * appropriate) must be called after the page is finished with, and
 * before put_page is called.
 *
 * If @nonblocking != NULL, __get_user_pages will not wait for disk IO
 * or mmap_sem contention, and if waiting is needed to pin all pages,
412 413 414 415 416 417 418 419
 * *@nonblocking will be set to 0.  Further, if @gup_flags does not
 * include FOLL_NOWAIT, the mmap_sem will be released via up_read() in
 * this case.
 *
 * A caller using such a combination of @nonblocking and @gup_flags
 * must therefore hold the mmap_sem for reading only, and recognize
 * when it's been released.  Otherwise, it must be held for either
 * reading or writing and will not be released.
420 421 422 423 424 425 426 427 428 429
 *
 * In most cases, get_user_pages or get_user_pages_fast should be used
 * instead of __get_user_pages. __get_user_pages should be used only if
 * you need some special @gup_flags.
 */
long __get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
		unsigned long start, unsigned long nr_pages,
		unsigned int gup_flags, struct page **pages,
		struct vm_area_struct **vmas, int *nonblocking)
{
430
	long i = 0;
431
	unsigned int page_mask;
432
	struct vm_area_struct *vma = NULL;
433 434 435 436 437 438 439 440 441 442 443 444 445 446 447

	if (!nr_pages)
		return 0;

	VM_BUG_ON(!!pages != !!(gup_flags & FOLL_GET));

	/*
	 * If FOLL_FORCE is set then do not force a full fault as the hinting
	 * fault information is unrelated to the reference behaviour of a task
	 * using the address space
	 */
	if (!(gup_flags & FOLL_FORCE))
		gup_flags |= FOLL_NUMA;

	do {
448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464
		struct page *page;
		unsigned int foll_flags = gup_flags;
		unsigned int page_increm;

		/* first iteration or cross vma bound */
		if (!vma || start >= vma->vm_end) {
			vma = find_extend_vma(mm, start);
			if (!vma && in_gate_area(mm, start)) {
				int ret;
				ret = get_gate_page(mm, start & PAGE_MASK,
						gup_flags, &vma,
						pages ? &pages[i] : NULL);
				if (ret)
					return i ? : ret;
				page_mask = 0;
				goto next_page;
			}
465

466 467 468 469 470 471 472
			if (!vma || check_vma_flags(vma, gup_flags))
				return i ? : -EFAULT;
			if (is_vm_hugetlb_page(vma)) {
				i = follow_hugetlb_page(mm, vma, pages, vmas,
						&start, &nr_pages, i,
						gup_flags);
				continue;
473
			}
474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498
		}
retry:
		/*
		 * If we have a pending SIGKILL, don't keep faulting pages and
		 * potentially allocating memory.
		 */
		if (unlikely(fatal_signal_pending(current)))
			return i ? i : -ERESTARTSYS;
		cond_resched();
		page = follow_page_mask(vma, start, foll_flags, &page_mask);
		if (!page) {
			int ret;
			ret = faultin_page(tsk, vma, start, &foll_flags,
					nonblocking);
			switch (ret) {
			case 0:
				goto retry;
			case -EFAULT:
			case -ENOMEM:
			case -EHWPOISON:
				return i ? i : ret;
			case -EBUSY:
				return i;
			case -ENOENT:
				goto next_page;
499
			}
500
			BUG();
501
		}
502 503 504 505 506 507 508
		if (IS_ERR(page))
			return i ? i : PTR_ERR(page);
		if (pages) {
			pages[i] = page;
			flush_anon_page(vma, page, start);
			flush_dcache_page(page);
			page_mask = 0;
509 510
		}
next_page:
511 512 513 514 515 516 517 518 519 520
		if (vmas) {
			vmas[i] = vma;
			page_mask = 0;
		}
		page_increm = 1 + (~(start >> PAGE_SHIFT) & page_mask);
		if (page_increm > nr_pages)
			page_increm = nr_pages;
		i += page_increm;
		start += page_increm * PAGE_SIZE;
		nr_pages -= page_increm;
521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550
	} while (nr_pages);
	return i;
}
EXPORT_SYMBOL(__get_user_pages);

/*
 * fixup_user_fault() - manually resolve a user page fault
 * @tsk:	the task_struct to use for page fault accounting, or
 *		NULL if faults are not to be recorded.
 * @mm:		mm_struct of target mm
 * @address:	user address
 * @fault_flags:flags to pass down to handle_mm_fault()
 *
 * This is meant to be called in the specific scenario where for locking reasons
 * we try to access user memory in atomic context (within a pagefault_disable()
 * section), this returns -EFAULT, and we want to resolve the user fault before
 * trying again.
 *
 * Typically this is meant to be used by the futex code.
 *
 * The main difference with get_user_pages() is that this function will
 * unconditionally call handle_mm_fault() which will in turn perform all the
 * necessary SW fixup of the dirty and young bits in the PTE, while
 * handle_mm_fault() only guarantees to update these in the struct page.
 *
 * This is important for some architectures where those bits also gate the
 * access permission to the page because they are maintained in software.  On
 * such architectures, gup() will not be enough to make a subsequent access
 * succeed.
 *
551
 * This has the same semantics wrt the @mm->mmap_sem as does filemap_fault().
552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573
 */
int fixup_user_fault(struct task_struct *tsk, struct mm_struct *mm,
		     unsigned long address, unsigned int fault_flags)
{
	struct vm_area_struct *vma;
	vm_flags_t vm_flags;
	int ret;

	vma = find_extend_vma(mm, address);
	if (!vma || address < vma->vm_start)
		return -EFAULT;

	vm_flags = (fault_flags & FAULT_FLAG_WRITE) ? VM_WRITE : VM_READ;
	if (!(vm_flags & vma->vm_flags))
		return -EFAULT;

	ret = handle_mm_fault(mm, vma, address, fault_flags);
	if (ret & VM_FAULT_ERROR) {
		if (ret & VM_FAULT_OOM)
			return -ENOMEM;
		if (ret & (VM_FAULT_HWPOISON | VM_FAULT_HWPOISON_LARGE))
			return -EHWPOISON;
574
		if (ret & (VM_FAULT_SIGBUS | VM_FAULT_SIGSEGV))
575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682
			return -EFAULT;
		BUG();
	}
	if (tsk) {
		if (ret & VM_FAULT_MAJOR)
			tsk->maj_flt++;
		else
			tsk->min_flt++;
	}
	return 0;
}

/*
 * get_user_pages() - pin user pages in memory
 * @tsk:	the task_struct to use for page fault accounting, or
 *		NULL if faults are not to be recorded.
 * @mm:		mm_struct of target mm
 * @start:	starting user address
 * @nr_pages:	number of pages from start to pin
 * @write:	whether pages will be written to by the caller
 * @force:	whether to force access even when user mapping is currently
 *		protected (but never forces write access to shared mapping).
 * @pages:	array that receives pointers to the pages pinned.
 *		Should be at least nr_pages long. Or NULL, if caller
 *		only intends to ensure the pages are faulted in.
 * @vmas:	array of pointers to vmas corresponding to each page.
 *		Or NULL if the caller does not require them.
 *
 * Returns number of pages pinned. This may be fewer than the number
 * requested. If nr_pages is 0 or negative, returns 0. If no pages
 * were pinned, returns -errno. Each page returned must be released
 * with a put_page() call when it is finished with. vmas will only
 * remain valid while mmap_sem is held.
 *
 * Must be called with mmap_sem held for read or write.
 *
 * get_user_pages walks a process's page tables and takes a reference to
 * each struct page that each user address corresponds to at a given
 * instant. That is, it takes the page that would be accessed if a user
 * thread accesses the given user virtual address at that instant.
 *
 * This does not guarantee that the page exists in the user mappings when
 * get_user_pages returns, and there may even be a completely different
 * page there in some cases (eg. if mmapped pagecache has been invalidated
 * and subsequently re faulted). However it does guarantee that the page
 * won't be freed completely. And mostly callers simply care that the page
 * contains data that was valid *at some point in time*. Typically, an IO
 * or similar operation cannot guarantee anything stronger anyway because
 * locks can't be held over the syscall boundary.
 *
 * If write=0, the page must not be written to. If the page is written to,
 * set_page_dirty (or set_page_dirty_lock, as appropriate) must be called
 * after the page is finished with, and before put_page is called.
 *
 * get_user_pages is typically used for fewer-copy IO operations, to get a
 * handle on the memory by some means other than accesses via the user virtual
 * addresses. The pages may be submitted for DMA to devices or accessed via
 * their kernel linear mapping (via the kmap APIs). Care should be taken to
 * use the correct cache flushing APIs.
 *
 * See also get_user_pages_fast, for performance critical applications.
 */
long get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
		unsigned long start, unsigned long nr_pages, int write,
		int force, struct page **pages, struct vm_area_struct **vmas)
{
	int flags = FOLL_TOUCH;

	if (pages)
		flags |= FOLL_GET;
	if (write)
		flags |= FOLL_WRITE;
	if (force)
		flags |= FOLL_FORCE;

	return __get_user_pages(tsk, mm, start, nr_pages, flags, pages, vmas,
				NULL);
}
EXPORT_SYMBOL(get_user_pages);

/**
 * get_dump_page() - pin user page in memory while writing it to core dump
 * @addr: user address
 *
 * Returns struct page pointer of user page pinned for dump,
 * to be freed afterwards by page_cache_release() or put_page().
 *
 * Returns NULL on any kind of failure - a hole must then be inserted into
 * the corefile, to preserve alignment with its headers; and also returns
 * NULL wherever the ZERO_PAGE, or an anonymous pte_none, has been found -
 * allowing a hole to be left in the corefile to save diskspace.
 *
 * Called without mmap_sem, but after all other threads have been killed.
 */
#ifdef CONFIG_ELF_CORE
struct page *get_dump_page(unsigned long addr)
{
	struct vm_area_struct *vma;
	struct page *page;

	if (__get_user_pages(current, current->mm, addr, 1,
			     FOLL_FORCE | FOLL_DUMP | FOLL_GET, &page, &vma,
			     NULL) < 1)
		return NULL;
	flush_cache_page(vma, addr, page_to_pfn(page));
	return page;
}
#endif /* CONFIG_ELF_CORE */
683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877

/*
 * Generic RCU Fast GUP
 *
 * get_user_pages_fast attempts to pin user pages by walking the page
 * tables directly and avoids taking locks. Thus the walker needs to be
 * protected from page table pages being freed from under it, and should
 * block any THP splits.
 *
 * One way to achieve this is to have the walker disable interrupts, and
 * rely on IPIs from the TLB flushing code blocking before the page table
 * pages are freed. This is unsuitable for architectures that do not need
 * to broadcast an IPI when invalidating TLBs.
 *
 * Another way to achieve this is to batch up page table containing pages
 * belonging to more than one mm_user, then rcu_sched a callback to free those
 * pages. Disabling interrupts will allow the fast_gup walker to both block
 * the rcu_sched callback, and an IPI that we broadcast for splitting THPs
 * (which is a relatively rare event). The code below adopts this strategy.
 *
 * Before activating this code, please be aware that the following assumptions
 * are currently made:
 *
 *  *) HAVE_RCU_TABLE_FREE is enabled, and tlb_remove_table is used to free
 *      pages containing page tables.
 *
 *  *) THP splits will broadcast an IPI, this can be achieved by overriding
 *      pmdp_splitting_flush.
 *
 *  *) ptes can be read atomically by the architecture.
 *
 *  *) access_ok is sufficient to validate userspace address ranges.
 *
 * The last two assumptions can be relaxed by the addition of helper functions.
 *
 * This code is based heavily on the PowerPC implementation by Nick Piggin.
 */
#ifdef CONFIG_HAVE_GENERIC_RCU_GUP

#ifdef __HAVE_ARCH_PTE_SPECIAL
static int gup_pte_range(pmd_t pmd, unsigned long addr, unsigned long end,
			 int write, struct page **pages, int *nr)
{
	pte_t *ptep, *ptem;
	int ret = 0;

	ptem = ptep = pte_offset_map(&pmd, addr);
	do {
		/*
		 * In the line below we are assuming that the pte can be read
		 * atomically. If this is not the case for your architecture,
		 * please wrap this in a helper function!
		 *
		 * for an example see gup_get_pte in arch/x86/mm/gup.c
		 */
		pte_t pte = ACCESS_ONCE(*ptep);
		struct page *page;

		/*
		 * Similar to the PMD case below, NUMA hinting must take slow
		 * path
		 */
		if (!pte_present(pte) || pte_special(pte) ||
			pte_numa(pte) || (write && !pte_write(pte)))
			goto pte_unmap;

		VM_BUG_ON(!pfn_valid(pte_pfn(pte)));
		page = pte_page(pte);

		if (!page_cache_get_speculative(page))
			goto pte_unmap;

		if (unlikely(pte_val(pte) != pte_val(*ptep))) {
			put_page(page);
			goto pte_unmap;
		}

		pages[*nr] = page;
		(*nr)++;

	} while (ptep++, addr += PAGE_SIZE, addr != end);

	ret = 1;

pte_unmap:
	pte_unmap(ptem);
	return ret;
}
#else

/*
 * If we can't determine whether or not a pte is special, then fail immediately
 * for ptes. Note, we can still pin HugeTLB and THP as these are guaranteed not
 * to be special.
 *
 * For a futex to be placed on a THP tail page, get_futex_key requires a
 * __get_user_pages_fast implementation that can pin pages. Thus it's still
 * useful to have gup_huge_pmd even if we can't operate on ptes.
 */
static int gup_pte_range(pmd_t pmd, unsigned long addr, unsigned long end,
			 int write, struct page **pages, int *nr)
{
	return 0;
}
#endif /* __HAVE_ARCH_PTE_SPECIAL */

static int gup_huge_pmd(pmd_t orig, pmd_t *pmdp, unsigned long addr,
		unsigned long end, int write, struct page **pages, int *nr)
{
	struct page *head, *page, *tail;
	int refs;

	if (write && !pmd_write(orig))
		return 0;

	refs = 0;
	head = pmd_page(orig);
	page = head + ((addr & ~PMD_MASK) >> PAGE_SHIFT);
	tail = page;
	do {
		VM_BUG_ON_PAGE(compound_head(page) != head, page);
		pages[*nr] = page;
		(*nr)++;
		page++;
		refs++;
	} while (addr += PAGE_SIZE, addr != end);

	if (!page_cache_add_speculative(head, refs)) {
		*nr -= refs;
		return 0;
	}

	if (unlikely(pmd_val(orig) != pmd_val(*pmdp))) {
		*nr -= refs;
		while (refs--)
			put_page(head);
		return 0;
	}

	/*
	 * Any tail pages need their mapcount reference taken before we
	 * return. (This allows the THP code to bump their ref count when
	 * they are split into base pages).
	 */
	while (refs--) {
		if (PageTail(tail))
			get_huge_page_tail(tail);
		tail++;
	}

	return 1;
}

static int gup_huge_pud(pud_t orig, pud_t *pudp, unsigned long addr,
		unsigned long end, int write, struct page **pages, int *nr)
{
	struct page *head, *page, *tail;
	int refs;

	if (write && !pud_write(orig))
		return 0;

	refs = 0;
	head = pud_page(orig);
	page = head + ((addr & ~PUD_MASK) >> PAGE_SHIFT);
	tail = page;
	do {
		VM_BUG_ON_PAGE(compound_head(page) != head, page);
		pages[*nr] = page;
		(*nr)++;
		page++;
		refs++;
	} while (addr += PAGE_SIZE, addr != end);

	if (!page_cache_add_speculative(head, refs)) {
		*nr -= refs;
		return 0;
	}

	if (unlikely(pud_val(orig) != pud_val(*pudp))) {
		*nr -= refs;
		while (refs--)
			put_page(head);
		return 0;
	}

	while (refs--) {
		if (PageTail(tail))
			get_huge_page_tail(tail);
		tail++;
	}

	return 1;
}

878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920
static int gup_huge_pgd(pgd_t orig, pgd_t *pgdp, unsigned long addr,
			unsigned long end, int write,
			struct page **pages, int *nr)
{
	int refs;
	struct page *head, *page, *tail;

	if (write && !pgd_write(orig))
		return 0;

	refs = 0;
	head = pgd_page(orig);
	page = head + ((addr & ~PGDIR_MASK) >> PAGE_SHIFT);
	tail = page;
	do {
		VM_BUG_ON_PAGE(compound_head(page) != head, page);
		pages[*nr] = page;
		(*nr)++;
		page++;
		refs++;
	} while (addr += PAGE_SIZE, addr != end);

	if (!page_cache_add_speculative(head, refs)) {
		*nr -= refs;
		return 0;
	}

	if (unlikely(pgd_val(orig) != pgd_val(*pgdp))) {
		*nr -= refs;
		while (refs--)
			put_page(head);
		return 0;
	}

	while (refs--) {
		if (PageTail(tail))
			get_huge_page_tail(tail);
		tail++;
	}

	return 1;
}

921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947
static int gup_pmd_range(pud_t pud, unsigned long addr, unsigned long end,
		int write, struct page **pages, int *nr)
{
	unsigned long next;
	pmd_t *pmdp;

	pmdp = pmd_offset(&pud, addr);
	do {
		pmd_t pmd = ACCESS_ONCE(*pmdp);

		next = pmd_addr_end(addr, end);
		if (pmd_none(pmd) || pmd_trans_splitting(pmd))
			return 0;

		if (unlikely(pmd_trans_huge(pmd) || pmd_huge(pmd))) {
			/*
			 * NUMA hinting faults need to be handled in the GUP
			 * slowpath for accounting purposes and so that they
			 * can be serialised against THP migration.
			 */
			if (pmd_numa(pmd))
				return 0;

			if (!gup_huge_pmd(pmd, pmdp, addr, next, write,
				pages, nr))
				return 0;

948 949 950 951 952 953 954 955
		} else if (unlikely(is_hugepd(__hugepd(pmd_val(pmd))))) {
			/*
			 * architecture have different format for hugetlbfs
			 * pmd format and THP pmd format
			 */
			if (!gup_huge_pd(__hugepd(pmd_val(pmd)), addr,
					 PMD_SHIFT, next, write, pages, nr))
				return 0;
956 957 958 959 960 961 962
		} else if (!gup_pte_range(pmd, addr, next, write, pages, nr))
				return 0;
	} while (pmdp++, addr = next, addr != end);

	return 1;
}

963 964
static int gup_pud_range(pgd_t pgd, unsigned long addr, unsigned long end,
			 int write, struct page **pages, int *nr)
965 966 967 968
{
	unsigned long next;
	pud_t *pudp;

969
	pudp = pud_offset(&pgd, addr);
970
	do {
971
		pud_t pud = READ_ONCE(*pudp);
972 973 974 975

		next = pud_addr_end(addr, end);
		if (pud_none(pud))
			return 0;
976
		if (unlikely(pud_huge(pud))) {
977
			if (!gup_huge_pud(pud, pudp, addr, next, write,
978 979 980 981 982
					  pages, nr))
				return 0;
		} else if (unlikely(is_hugepd(__hugepd(pud_val(pud))))) {
			if (!gup_huge_pd(__hugepd(pud_val(pud)), addr,
					 PUD_SHIFT, next, write, pages, nr))
983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027
				return 0;
		} else if (!gup_pmd_range(pud, addr, next, write, pages, nr))
			return 0;
	} while (pudp++, addr = next, addr != end);

	return 1;
}

/*
 * Like get_user_pages_fast() except it's IRQ-safe in that it won't fall back to
 * the regular GUP. It will only return non-negative values.
 */
int __get_user_pages_fast(unsigned long start, int nr_pages, int write,
			  struct page **pages)
{
	struct mm_struct *mm = current->mm;
	unsigned long addr, len, end;
	unsigned long next, flags;
	pgd_t *pgdp;
	int nr = 0;

	start &= PAGE_MASK;
	addr = start;
	len = (unsigned long) nr_pages << PAGE_SHIFT;
	end = start + len;

	if (unlikely(!access_ok(write ? VERIFY_WRITE : VERIFY_READ,
					start, len)))
		return 0;

	/*
	 * Disable interrupts.  We use the nested form as we can already have
	 * interrupts disabled by get_futex_key.
	 *
	 * With interrupts disabled, we block page table pages from being
	 * freed from under us. See mmu_gather_tlb in asm-generic/tlb.h
	 * for more details.
	 *
	 * We do not adopt an rcu_read_lock(.) here as we also want to
	 * block IPIs that come from THPs splitting.
	 */

	local_irq_save(flags);
	pgdp = pgd_offset(mm, addr);
	do {
1028 1029
		pgd_t pgd = ACCESS_ONCE(*pgdp);

1030
		next = pgd_addr_end(addr, end);
1031
		if (pgd_none(pgd))
1032
			break;
1033 1034 1035 1036 1037 1038 1039 1040 1041
		if (unlikely(pgd_huge(pgd))) {
			if (!gup_huge_pgd(pgd, pgdp, addr, next, write,
					  pages, &nr))
				break;
		} else if (unlikely(is_hugepd(__hugepd(pgd_val(pgd))))) {
			if (!gup_huge_pd(__hugepd(pgd_val(pgd)), addr,
					 PGDIR_SHIFT, next, write, pages, &nr))
				break;
		} else if (!gup_pud_range(pgd, addr, next, write, pages, &nr))
1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097
			break;
	} while (pgdp++, addr = next, addr != end);
	local_irq_restore(flags);

	return nr;
}

/**
 * get_user_pages_fast() - pin user pages in memory
 * @start:	starting user address
 * @nr_pages:	number of pages from start to pin
 * @write:	whether pages will be written to
 * @pages:	array that receives pointers to the pages pinned.
 *		Should be at least nr_pages long.
 *
 * Attempt to pin user pages in memory without taking mm->mmap_sem.
 * If not successful, it will fall back to taking the lock and
 * calling get_user_pages().
 *
 * Returns number of pages pinned. This may be fewer than the number
 * requested. If nr_pages is 0 or negative, returns 0. If no pages
 * were pinned, returns -errno.
 */
int get_user_pages_fast(unsigned long start, int nr_pages, int write,
			struct page **pages)
{
	struct mm_struct *mm = current->mm;
	int nr, ret;

	start &= PAGE_MASK;
	nr = __get_user_pages_fast(start, nr_pages, write, pages);
	ret = nr;

	if (nr < nr_pages) {
		/* Try to get the remaining pages with get_user_pages */
		start += nr << PAGE_SHIFT;
		pages += nr;

		down_read(&mm->mmap_sem);
		ret = get_user_pages(current, mm, start,
				     nr_pages - nr, write, 0, pages, NULL);
		up_read(&mm->mmap_sem);

		/* Have to be a bit careful with return values */
		if (nr > 0) {
			if (ret < 0)
				ret = nr;
			else
				ret += nr;
		}
	}

	return ret;
}

#endif /* CONFIG_HAVE_GENERIC_RCU_GUP */